Same University

Italy

Same University

Italy
SEARCH FILTERS
Time filter
Source Type

Shafii N.,University of Aveiro | Kasaei S.H.,University of Aveiro | Lopes L.S.,University of Aveiro | Lopes L.S.,Same University
Proceedings - 2016 International Conference on Autonomous Robot Systems and Competitions, ICARSC 2016 | Year: 2016

Enabling a robot to grasp unknown objects is still an ongoing challenge in robotics. The main problem is to find an appropriate grasp configuration including the position and orientation of the arm relative to the object and fingers configuration. One approach is to recognize an appropriate grasp pose for an object based on one or more grasp demonstrations of the same or other objects. We focus on familiar objects, i.e. unknown objects sharing some features with known objects. The underlying assumption in grasping familiar objects is that, where they are similar to known ones, they may be grasped in a similar way. However finding an object representation and a similarity metric are still the main challenge to transfer grasp experiences to new objects. In this paper, we present an interactive object view recognition approach and a similarity metric to grasp familiar objects. Object view recognition is incrementally capable of recognizing object view labels. The grasp pose learning approach learns a grasp template for a recognized object view using local and global visual features of a demonstrated grasp. In grasp pose recognition, a similarity measure based on Mahalanobis distance is used for grasp template matching. The experimental results reveal the high reliability of the developed template matching approach. We also demonstrate how the proposed grasp learning system can incrementally improve its performance in grasping familiar objects. © 2016 IEEE.


Kasaei S.H.,University of Aveiro | Lopes L.S.,University of Aveiro | Lopes L.S.,Same University | Tome A.M.,University of Aveiro | Tome A.M.,Same University
Proceedings - 2016 International Conference on Autonomous Robot Systems and Competitions, ICARSC 2016 | Year: 2016

In open-ended domains, autonomous robots must have the ability to continuously process visual information, and execute learning and recognition in a concurrent and interleaved fashion. Because the set of categories to be learned is not predefined, it is not feasible to assume that one can pre-program all object categories required by service robots. Topic modelling approaches usually construct the topics from a training set to recognize objects. However, in open-ended domains, the data available for training increases continuously. If limited training data is used, this might lead to non-discriminative topics and, as a consequence, to poor object recognition performance. This paper proposes an object recognition system capable of learning object categories as well as the topics used to encode objects concurrently and in an open-ended manner. This system provides a robot with the capabilities to, (i) use unsupervised object exploration to construct a dictionary of visual words for representing objects and (ii) conceptualize object experiences and learn new object categories using topic modelling and human feedback. To examine the performance of the system, an on-line evaluation protocol is used to assess the performance of the system in an open-ended setting. The experimental results show the fulfilling performance of this approach on different types of objects. © 2016 IEEE.


Song B.,University of California at Riverside | Ding C.,Same University | Kamal A.T.,Same University | Farrell J.A.,University of California at Riverside | Roy-Chowdhury A.K.,Research Projects Include Intelligent Camera Networks
IEEE Signal Processing Magazine | Year: 2011

Over the past decade, large-scale camera networks have become increasingly prevalent in a wide range of applications, such as security and surveillance, disaster response, and environmental modeling. In many applications, bandwidth constraints, security concerns, and difficulty in storing and analyzing large amounts of data centrally at a single location necessitate the development of distributed camera network architectures. Thus, the development of distributed scene-analysis algorithms has received much attention lately. However, the performance of these algorithms often suffers because of the inability to effectively acquire the desired images, especially when the targets are dispersed over a wide field of view (FOV). In this article, we show how to develop an end-to-end framework for integrated sensing and analysis in a distributed camera network so as to maximize various scene-understanding performance criteria (e.g., tracking accuracy, best shot, and image resolution). We show how the existing work in autonomous multiagent systems can be leveraged for this purpose, more specifically, game theory-based distributed optimization algorithms for dynamic camera network reconfiguration and consensus algorithms for scene analysis. An experimental test bed for evaluating such work is described, and the comparisons against other approaches are provided. The results from a reallife camera network are also presented. © 2006 IEEE.


Huang J.,University of Adelaide | Radford A.,Same University
Architectural Research Quarterly | Year: 2013

Troppo Architects was established in Darwin, northern Australia, in 1981. The radical 'Troppo Style' of their houses ed in the 1980s blur edges between indoors and outdoors, formality and informality, and enclosure and openness. In this paper a corpus of ten of those houses is examined through the lens of philosopher Warwick Fox's concept of responsive cohesion. This is a unique quality of the relations between the internal components of a 'thing' and also between the 'thing' and its contexts. The houses are exemplary in demonstrating this quality of mutual and subtle response through the interactions between their form and local environmental and cultural contexts, including the idea of responsible hedonism as a principle. The research utilises original documents, site visits and interviews with stakeholders, particularly the architects and the residents. The outcomes reveal interlocking links between the dwelling, the place, the values of the architects and their clients, and the global bio-physical world. They show objectives of personal enjoyment of life and environmental responsibility could co-exist in harmony. However, the research also shows how these houses change over time depending on their location and on the attitudes of their owners. They would not work elsewhere, or for clients without a similar attitude to life and the pleasures offered by everyday living close to the variety and stimuli of the outdoors. © 2013 Cambridge University Press.


Amirante A.,Same University | Castaldi T.,Same University | Miniero L.,Same University | Romano S.P.,University of Naples Federico II
IEEE Communications Magazine | Year: 2011

In this article we present Meetecho Mobile, an innovative conferencing client designed for mobile devices. Such a client provides access to conferences compliant with the most recent standard proposals currently under definition within the IETF. It allows mobile users to participate in multimedia conferences involving, besides an XMPP-based chat, both audio and video streams. The article discusses the design and implementation of the conferencing client and highlights the most notable solutions we devised in order to effectively handle a whole suite of protocols, ranging from signaling (SIP/SDP, XMPP) to real-time streaming (RTP). We also provide information about the main performance figures characterizing the client's behavior. © 2011 IEEE.


Amirante A.,Meetecho S.r.l. | Castaldi T.,University of Naples Federico II | Miniero L.,Same University | Romano S.,University of Naples
IEEE Communications Magazine | Year: 2013

The growing interest in integrating interactive multimedia features into web applications has recently led to the creation of the W3C WebRTC and the IETF RTCWEB working groups. Such groups are jointly defining both the application programming interfaces and the underlying communication protocols for the setup and management of a reliable communication path between any pair of next-generation web browsers. While the ongoing work is focusing on peer-to-peer communication between browsers, engineers are also facing a new issue, associated with the coexistence of legacy SIPbased systems with the upcoming browserenabled architectures. We herein discuss how we tackled such an issue, by first identifying interoperability requirements and then presenting a real-world interoperability example dealing with the integration of RTCWEB clients into an existing standards-based collaboration platform. © 1979-2012 IEEE.


Mikic-Fonte F.A.,University of Vigo | Mikic-Fonte F.A.,Same University | Burguillo-Rial J.C.,University of Vigo | Burguillo-Rial J.C.,Same University | And 4 more authors.
Proceedings - Frontiers in Education Conference, FIE | Year: 2010

INES (INtelligent Educational System) is an operative prototype of an e-learning platform, which counts with functionalities of Learning Management Systems, Learning Content Management Systems, and Intelligent Tutoring Systems. To achieve these functionalities, our system includes several tools and technologies, such as: i) semantic management of users and contents; ii) an conversational agent to communicate with students in natural language; iii) BDI-based (Believes, Desires, Intentions) agents, which shape the tutoring module of the system; iv) an inference engine; and v) ontologies, to semantically model the users, their activities, and the learning contents. At the present paper we will address the intelligent tutoring module, and more specifically, its BDI-based agents. Briefly, the tasks of these agents are to recognize each student (checking his/her system credentials) and to obtain information about his/her learning progress. So, it can be able to suggest to each one specific tasks to achieve his/her particular learning objectives. The student himself/herself will decide if he/she accepts these tasks or ask for other ones. These new requested tasks can be delivered or not by the intelligent tutoring module, taking into account its decisions, which are based in several parameters related to the existing learning paths and the student's profile. © 2010 IEEE.

Loading Same University collaborators
Loading Same University collaborators